Keynote Lectures
Anusaaraka: An approach to Machine Translation
Akshar Bharati, Vineet
Chaitanya1,
1Rashtriya Sanskrit Vidyapeetha,
2 Department of Sanskrit Studies
{vc9999999@gmail.com,
apksh@uohyd.ernet.in}
Rule based Machine
Translation (MT) needs lot of effort of "100 man years" or so. On the
other hand Statistical methods need aligned bilingual corpus of substantial
size (1.5 million words or more). Can we not benefit from the large bilingual
population that
We describe “Anusaaraka - an approach to Machine
Translation”
A) Which takes
advantage of
1. existing
software tools for analyzing English language,
2. existing Bilingual
English-Hindi dictionary, and
3. existing
architecture for MT,
all of
which are available under General Public License.
B) which has the following features:
Anusaaraka thus serves as a reading aid
promising 100% comprehension with a little effort.
C) which also serves
as a work-bench for NLP students
On Estimating Probability Mass Functions from Small Samples
Sanjeev P. Khudanpur
The
Probabilistic models, with parameters estimated from
sample data, are pervasive in natural language processing, as is the
concomitant and age old problem of estimating the necessary probabilities from
data. A novel and insightful view of a recurring problem in this
context will be presented, namely the problem of estimating a probability
mass function (pmf) for a discrete random variable from a small
sample. Formally, a pmf will be deemed admissible as an
estimate if it assigns merely a higher likelihood to the observed value of
a sufficient statistic than to any other value possible for the same
sample size. The standard maximum likelihood estimate is trivially
admissible by this definition, but so are many other pmfs. It will
be shown that the principled selection of an estimate from this admissible
family via criteria such as minimum divergence leads to inherently
smooth estimates that make no prior assumptions about the unknown
probability while still providing a way to incorporate prior domain knowledge
when available. Widely prevalent practices such as discounting the
probability of seen events, and ad hoc procedures such as back-off
estimates of conditional pmfs, will be shown to be natural consequences of this
viewpoint. Some newly developed theoretical guarantees on the accuracy of
the estimates will be provided and empirical results in statistical
language modeling will be presented to demonstrate the computational
feasibility of the proposed methods.
Towards
Word Sense Disambiguation in the Large
Hwee Tou Ng
{nght@comp.nus.edu.sg}
Word sense disambiguation (WSD) is the task of
determining the correct meaning or sense of a word in context. A critical
problem faced by current supervised WSD systems is the lack of manually
annotated training data. Tackling this data acquisition bottleneck is crucial, in
order to build WSD systems with broad coverage of words. In this talk, I will
present results of our attempt to scale up WSD, exploiting large quantities of
Chinese-English parallel text. Our evaluation indicates that our implemented
approach of gathering training examples from parallel text is promising, when
tested on nouns and adjectives of SENSEVAL-2 and SENSEVAL-3 English all-words
task. This work is jointly done with Yee Seng Chan.
The
Semantic Quilt: Contexts, Co-occurrences, Kernels, and Ontologies
Ted Pedersen
{tpederse@d.umn.edu}
Determining the meaning of words and phrases in text has
been a central problem in Natural Language Processing for
many years. As a result, there is a
wealth of approaches available, including knowledge based methods, unsupervised
clustering approaches, and supervised learning techniques. At present these
methods are generally used independently to good but limited effect. In this
talk I will provide an overview of these approaches, and show how they can be
combined into a single framework that expands their coverage
and effectiveness well beyond their individual capabilities.